© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31515
    Prev
    Next
    INDEX
    Explanations

    questions starting with which of these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Quanto
    0.57
    ה
    0.52
    CUSSION
    0.50
    ל
    0.49
    fptr
    0.48
    בא
    0.48
     കുടും
    0.47
    ミ
    0.47
    К
    0.47
    СТ
    0.46
    POSITIVE LOGITS
    队的
    0.48
    ur
    0.48
     तापमान
    0.46
    irsty
    0.45
    த்தில்
    0.45
     southwestern
    0.45
    荞
    0.44
     chess
    0.43
    ällen
    0.43
    Route
    0.43
    Activations Density 0.000%

    No Known Activations